Jones Seminar: The Shape of Information

Optional ZOOM LINK

We live in an era, rich in information, which comes in many forms—sounds, signals, graphs, images and more, and information often manifests itself in its "shape." Hence, the understanding this shape can enhance one's understanding of information, leading one to ask fundamental questions such as:

1. How many samples do I need to take to recover an RF signal?
2. What is an intrinsic dimension of this hyper-spectral image?
3. How can I find hidden communities in a social network?

—just to name a few.

In the talk, I will describe how studying the geometry and topology of this shape (sometimes, something as simple as counting the number of non-zero components of a vector) can positively impact what one can learn from information.

Hosted by Professor George Cybenko.

About the Speaker(s)

Peter Chin
Professor of Engineering, Dartmouth

Peter Chin is a professor of engineering at Dartmouth where he leads LISP—Learning, Intelligence + Signal Processing—Lab. He and his students are investigating fundamental questions such as, "Can Intelligence be learned?" at the intersection of signal processing, machine learning, game theory, differential geometry, extremal graph theory, and computational neuroscience. He is currently an associate editor of IEEE Transactions on Computational Social Systems, and has served as co–chair of the annual SPIE/DSS Conference on Cyber Sensing, and symposium chair of the GlobalSIP conference. His lab's research has been funded by NSF, NIH, DARPA, AFOSR, ONR, and others and has been presented at NeurIPS, ICLR, COLT, ISIT, ICASSP, and other venues. He is a Phi Beta Kappa graduate of Duke University where he was a triple major in math, computer science and electrical engineering and received his PhD in mathematics from MIT.

Contact

For more information, contact Ashley Parker at ashley.l.parker@dartmouth.edu.